Stationary Markov Nash Equilibria for Nonzero-Sum Constrained ARAT Markov Games.
François DufourTomás Prieto-RumeauPublished in: SIAM J. Control. Optim. (2022)
Keyphrases
- nash equilibria
- markov games
- stochastic games
- multiagent reinforcement learning
- nash equilibrium
- game theory
- markov decision processes
- incomplete information
- game theoretic
- non stationary
- pure strategy
- markov chain
- reinforcement learning algorithms
- markov model
- reinforcement learning
- machine learning
- multi agent
- objective function
- multiagent systems
- dynamic programming
- special case
- finite horizon
- mixed strategy